diff --git a/wrangler_functions.py b/wrangler_functions.py
index 9d2363334ec2f9b7dd4e0935f7a071e8975bf280..132e6c9fc8f472512efec836f0512c9e8a66bf4f 100644
--- a/wrangler_functions.py
+++ b/wrangler_functions.py
@@ -76,7 +76,7 @@ output_schema = {"GBIF_download_doi": "str",
# Core functions >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
-def build_output_database(output_database):
+def build_output_database(output_database: str) -> None:
"""
Create a database for storing occurrence and taxon concept data.
The column names that are "camel case" are Darwin Core attributes, whereas
@@ -86,7 +86,7 @@ def build_output_database(output_database):
Parameters
----------
- output_database : Path for sqlite database to create; string.
+ output_database : Path for sqlite database to create
Returns
-------
@@ -108,8 +108,8 @@ def build_output_database(output_database):
return
-def get_EBD_records(taxon_info, filter_set, working_directory, EBD_file,
- query_name, R_home):
+def get_EBD_records(taxon_info: dict, filter_set: dict, working_directory: str, EBD_file: str,
+ query_name: str, R_home: str) -> pd.DataFrame:
'''
Gets eBird records from a copy of the Ebird Basic Dataset that you
acquired. Primarily runs R code that uses the Auk package to query the
@@ -119,12 +119,12 @@ def get_EBD_records(taxon_info, filter_set, working_directory, EBD_file,
Parameters
----------
- taxon_info : your taxon concept; dictionary
- filter_set : name of the filter set to apply; dictionary
- working_directory : path to use for table of filtered query results; string
- EBD_file : path to your downloaded copy of the Ebird Basic Dataset; string
- query_name : the name you chose for your query; string
- R_home : path to R install to use, get from wranglerconfig; string
+ taxon_info : your taxon concept
+ filter_set : name of the filter set to apply
+ working_directory : path to use for table of filtered query results
+ EBD_file : path to your downloaded copy of the Ebird Basic Dataset
+ query_name : the name you chose for your query
+ R_home : path to R install to use, get from wranglerconfig
Returns
-------
@@ -449,8 +449,8 @@ def get_EBD_records(taxon_info, filter_set, working_directory, EBD_file,
return records2
-def get_GBIF_records(taxon_info, filter_set, query_name, working_directory,
- username, password, email):
+def get_GBIF_records(taxon_info: dict, filter_set: dict, query_name: str, working_directory: str,
+ username: str, password: str, email: str) -> pd.DataFrame:
'''
Retrieves species occurrence records from GBIF. Filters occurrence
records, buffers the xy points, and saves them in a database. Finally,
@@ -461,13 +461,13 @@ def get_GBIF_records(taxon_info, filter_set, query_name, working_directory,
Parameters
----------
- taxon_info : your taxon concept; dictionary
- filter_set : name of the filter set to apply; dictionary
- query_name : the name you chose for your query; string
- working_directory : path to use for table of filtered query results; string
- username : your GBIF username; string
- password : your GBIF password; string
- email : the email account associated with your GBIF account; string
+ taxon_info : your taxon concept
+ filter_set : name of the filter set to apply
+ query_name : the name you chose for your query
+ working_directory : path to use for table of filtered query results
+ username : your GBIF username
+ password : your GBIF password
+ email : the email account associated with your GBIF account
Returns
-------
@@ -781,8 +781,8 @@ def get_GBIF_records(taxon_info, filter_set, query_name, working_directory,
return records2
-def process_records(ebird_data, gbif_data, filter_set, taxon_info,
- working_directory, query_name):
+def process_records(ebird_data: pd.DataFrame, gbif_data: pd.DataFrame, filter_set: str, taxon_info: dict,
+ working_directory: dict, query_name: str) -> pd.DataFrame:
'''
Summarizes the values in the data frames, populates some fields,
apply filters, summarize what values persisted after filtering. Insert
@@ -1117,7 +1117,7 @@ def process_records(ebird_data, gbif_data, filter_set, taxon_info,
return None
-def nominal_precisions(longitude, latitude, produce):
+def nominal_precisions(longitude: str, latitude: str, produce: str) -> float:
'''
Calculates the nominal precisions based on WGS84 coordinates.
Method is based on information from wikipedia page on latitude and posts at
@@ -1158,7 +1158,7 @@ def nominal_precisions(longitude, latitude, produce):
return y
-def drop_duplicates_latlongdate(df):
+def drop_duplicates_latlongdate(df: pd.DataFrame) -> pd.DataFrame:
'''
Function to find and remove duplicate occurrence records within the
wildlife wrangler workflow. When duplicates exist, the record with the
@@ -1309,7 +1309,7 @@ def drop_duplicates_latlongdate(df):
return df2
-def verify_results(database):
+def verify_results(database: str) -> None:
'''
Compares the occurrence record attributes to the filters that were
supposed to be applied.
@@ -1317,7 +1317,7 @@ def verify_results(database):
Parameters
----------
- database : path to a wrangler output database; string.
+ database : path to a wrangler output database
Like "Z:/Occurrence_Records/test1.sqlite"
RESULTS
@@ -1474,14 +1474,14 @@ def verify_results(database):
# Helper functions >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
-def get_GBIF_code(name, rank='species'):
+def get_GBIF_code(name: str, rank: str ='species') -> str:
"""
Returns the GBIF species code for a scientific name.
Parameters
----------
- name : Scientific name; string
- rank : level of taxonomic hieriarchy to search; string
+ name : Scientific name
+ rank : level of taxonomic hieriarchy to search
Returns
-------
@@ -1493,7 +1493,7 @@ def get_GBIF_code(name, rank='species'):
return key
-def coord_rounded(x: str, digits: int):
+def coord_rounded(x: str, digits: int) -> str:
'''
Rounds a decimal degrees coordinate value to a specified precision (number
of digits). Returns pd.NA when a bad value is encountered. Works for
@@ -1520,15 +1520,13 @@ def coord_rounded(x: str, digits: int):
return pd.NA
-def get_record_details(key):
+def get_record_details(key: int) -> dict:
"""
Get the details of a records from GBIF
Parameters
----------
key : a gbif taxon code
- name : Scientific name; string
- rank : level of taxonomic hieriarchy to search; string
Returns
-------
@@ -1578,7 +1576,7 @@ def nominal_x_precision(dataframe: pd.DataFrame, lat_column: str,
return df
-def ccw_wkt_from_shapefile(shapefile, out_txt):
+def ccw_wkt_from_shapefile(shapefile: str, out_txt: str) -> None:
"""
Creates wkt with coordinates oriented counter clockwise for a given
shapefile. Shapefiles are oriented clockwise, which is incompatible with
@@ -1587,8 +1585,8 @@ def ccw_wkt_from_shapefile(shapefile, out_txt):
Parameters
----------
- shapefile : path to the shpefile to read; string
- out_txt : path to the text file to write the wkt to; string
+ shapefile : path to the shpefile to read
+ out_txt : path to the text file to write the wkt to
Returns
-------
@@ -1629,14 +1627,14 @@ def ccw_wkt_from_shapefile(shapefile, out_txt):
return
-def spatial_output(database, make_file, mode, output_file=None, epsg=4326):
+def spatial_output(database: str, make_file: bool, mode: str, output_file: str =None, epsg: int = 4326):
'''
Creates a shapefile of species occurrence records from a wildlife wrangler
output SQLite database.
Parameters
----------
- database : the sqlite database to use; string (path)
+ database : the sqlite database to use
make_file : whether to save a shapefile. False just returns a geodatframe.
mode : three options: 1) "points" merely creates points from record
coordinates.
@@ -1756,7 +1754,7 @@ def spatial_output(database, make_file, mode, output_file=None, epsg=4326):
return out
-def CONUS_bbox():
+def CONUS_bbox() -> tuple:
"""
Returns the bounding box of the conterminous U.S. as a tuple.
"""